Identifying Protein-Protein Interaction using Tree-Transformers and Heterogeneous Graph Neural Network
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
For a better understanding of the underlying biological mechanisms, it is crucial to identify the reciprocity between proteins. Often, extracting such interactions between proteins from biomedical articles faces challenges due to the complex sentence structure of the textual information sources. Most of the prominent previous works have applied additional hand-crafted features for the protein-protein interaction task. In this work, we have utilized two tree-structured attention-based neural network models along with a heterogeneous graph approach to perform this task. We suggest that the proposed model preserves the syntactic as well as the semantic information of the text. The experimental results demonstrate that even without using any additional feature extraction techniques, this model achieves significant performance boosts when applied on the five standard benchmark corpora compared to the previous works.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it